AWS Certified Machine Learning Engineer Associate · Free Practice Question Medium

Question 44

You are evaluating the performance of a machine learning model and want to ensure that it generalizes well on unseen data. You decide to partition your dataset into three distinct sets: training, validation, and testing. However, your model performs exceptionally well on the training set but poorly on the validation and test sets. What is the likely cause of this performance discrepancy?

  • A

    The model is underfitting the data.

  • B

    The training set is too small for meaningful evaluation.

  • C

    The model is overfitting the training data.

  • D

    The model has a high bias and low variance.

Reveal correct answer

Correct answer: C

A.

Underfitting leads to poor performance on both the training and test datasets, which is not the case here.

B.

While the size of the training set can influence performance, this scenario is primarily due to overfitting, not the dataset size.

C.

Overfitting occurs when the model performs well on the training data but poorly on unseen data, such as the validation and test sets. This happens because the model learns the noise and intricate details of the training data, reducing its generalizability.

D.

A high bias indicates underfitting, where the model is too simplistic, and a low variance suggests it doesn’t capture the complexity of the data, which would result in poor performance across all datasets.

Discussion

Think the marked answer is wrong, or have a better explanation? Share it below — comments appear after review.

You must be logged in to post a comment.

Preparing For

Your Certification?

255+ certifications
Detailed explanations
Free PDF samples

Has All The Questions You Need